SOTAVerified

Human motion prediction

Action prediction is a pre-fact video understanding task, which focuses on future states, in other words, it needs to reason about future states or infer action labels before the end of action execution.

Papers

Showing 110 of 162 papers

TitleStatusHype
MoMask: Generative Masked Modeling of 3D Human MotionsCode3
BAD: Bidirectional Auto-regressive Diffusion for Text-to-Motion GenerationCode2
InterDiff: Generating 3D Human-Object Interactions with Physics-Informed DiffusionCode2
HumanMAC: Masked Motion Completion for Human Motion PredictionCode2
Multi-Transmotion: Pre-trained Model for Human Motion PredictionCode1
Learning Semantic Latent Directions for Accurate and Controllable Human Motion PredictionCode1
Context-based Interpretable Spatio-Temporal Graph Convolutional Network for Human Motion ForecastingCode1
GCNext: Towards the Unity of Graph Convolutions for Human Motion PredictionCode1
Auxiliary Tasks Benefit 3D Skeleton-based Human Motion PredictionCode1
TransFusion: A Practical and Effective Transformer-based Diffusion Model for 3D Human Motion PredictionCode1
Show:102550
← PrevPage 1 of 17Next →

No leaderboard results yet.